Scholarlink

<p>To address the challenge of training reinforcement learning (RL) networks with limited data in Human-Robot Interaction (HRI), we introduce a novel task-oriented update method that combines meta-inverse reinforcement learning (Meta-IRL) and transformer encoder architectures. Our approach utilizes Meta-IRL to emulate expert trajectories, improving training efficiency by minimizing ineffective interactions. Through a systematic exploration of transformer encoder components, including varying heads and layers, we optimize feature extraction for sparse data representations. Experimental validation shows performance improvements in reinforcement learning networks trained with limited HRI expert demonstration data from Applied Behavior Analysis (ABA) scenarios.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing Reinforcement Learning with Limited HRI Demonstrations: A Task-Oriented Weight Update Method with Analysis of Multi-head and Layer Feature Combinations

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月8日

查看全文
  • Qinghua Chen,
  • Jessica Korneder,
  • Osamah A. Rawashdeh,
  • Yanfeng Wang,
  • Wing-Yue Geoffrey Louie

摘要

To address the challenge of training reinforcement learning (RL) networks with limited data in Human-Robot Interaction (HRI), we introduce a novel task-oriented update method that combines meta-inverse reinforcement learning (Meta-IRL) and transformer encoder architectures. Our approach utilizes Meta-IRL to emulate expert trajectories, improving training efficiency by minimizing ineffective interactions. Through a systematic exploration of transformer encoder components, including varying heads and layers, we optimize feature extraction for sparse data representations. Experimental validation shows performance improvements in reinforcement learning networks trained with limited HRI expert demonstration data from Applied Behavior Analysis (ABA) scenarios.